skills.rest
GRIND-Lab-Core
GRIND-Lab-CoreOFFICIAL
Explore all skills by this author →
WebsiteGitHub

training-check

Monitor spatial experiments and classify statuses as OK, STALLED, FAILED, or COMPLETE.

100|24|Updated Mar 31, 2026
Search Tags:#alerting#process control#experiment monitoring#status classification#spatial experiments
One-click install
npx skills add https://github.com/GRIND-Lab-Core/night_owl_research_agent --skill training-check-grind-lab-core
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: training-check
Source: https://github.com/GRIND-Lab-Core/night_owl_research_agent/tree/main/skills/training-check
Command: npx skills add https://github.com/GRIND-Lab-Core/night_owl_research_agent --skill training-check-grind-lab-core

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

The skill solves the problem of inefficient spatial experiments by monitoring and classifying their status, allowing for timely interventions and avoiding wasted computation time.

Core Features & Use Cases

  • Experiment Monitoring: Regularly checks active experiments for status and errors.
  • Status Classification: Classifies experiments as OK, STALLED, FAILED, or COMPLETE.
  • Alerting: Fires alerts by appending to output/PROJ_NOTES.md.
  • Human Checkpoint: Allows for human intervention during critical points to ensure data integrity.

Quick Start

Start monitoring experiments by running the skill in the context of the research-pipeline.

Frequently Asked Questions about training-check

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I monitor spatial experiment status to avoid wasted computation time?▼

Monitoring spatial experiment status involves regularly checking active computational processes and classifying them as OK, STALLED, FAILED, or COMPLETE. This allows for timely interventions and efficient experiment management.

What is process control for computational experiments and when do I need it?▼

Process control for computational experiments is the mechanism of monitoring active spatial data analysis runs for errors and status changes. You need it when running lengthy workflows where stalled or failed computations would waste significant time.

How do I set up experiment alerting for spatial data analysis workflows?▼

Experiment alerting for spatial data workflows is configured by running status monitoring scripts within the research-pipeline. The system fires alerts by appending status classifications and error details directly to the output/PROJ_NOTES.md file.

Does experiment monitoring work within an existing research-pipeline?▼

Yes, experiment monitoring is designed to run in the context of an existing research-pipeline. It regularly checks active spatial experiments and classifies their status without requiring external dependencies.

How do I trigger a human checkpoint during a failed spatial experiment?▼

A human checkpoint during a failed spatial experiment is triggered when the monitoring system classifies the status as FAILED or STALLED. This allows for manual intervention to ensure data integrity before computation continues.

Related Skills

Explore More Data & Analytics Skills→
GRIND-Lab-CoreGRIND-Lab-Core
100

full-pipeline

Orchestrate research pipelines from idea discovery to report generation.

Official
Advanced
crgarcia12crgarcia12

audit-log

Append structured audit log entries to a specified file.

Community
Intermediate
NITISH-gitbitNITISH-gitbit

bioinformatics

Access a unified repository of bioinformatics skills for genomic analysis workflows.

Community
Advanced
clawpod-appclawpod-app
46

deploy-monitor

Aggregate CI/CD deployment status and post-deploy health metrics into deterministic reports.

Community
Advanced